Lung Metastasis Probability in Ewing Sarcoma: A Nomogram Based on the SEER Database

Background. Up to now, an accurate nomogram to predict the lung metastasis probability in Ewing sarcoma (ES) at initial diagnosis is lacking. Our objective was to construct and validate a nomogram for the prediction of lung metastasis in ES patients. Methods. A total of 1157 patients with ES from the Surveillance, Epidemiology, and End Results (SEER) database were retrospectively collected. The predictors of lung metastasis were identified via the least absolute shrinkage and selection operator (LASSO) and multivariate logistic analysis. The discrimination and calibration of the nomogram were validated by receiver operating characteristic (ROC) curve and calibration curve. Decision curve analysis (DCA) was used to evaluate the clinical usefulness and net benefits of the prediction model. Results. Factors including age, tumor size, primary site, tumor extension, and other site metastasis were identified as the ultimate predictors for the nomogram. The calibration curves for the training and validation cohorts both revealed good agreement, and the Hosmer–Lemeshow test identified that the model was well fitted (p > 0.05). In addition, the area under the ROC curve (AUC) values in the training and validation cohorts were 0.732 (95% confidence interval, CI: 0.607–0.808) and 0.741 (95% CI: 0.602–0.856), respectively, indicating good predictive discrimination. The DCA showed that when the predictive metastasis probability was between 1% and 90%, the nomogram could provide clinical usefulness and net benefit. Conclusion. The nomogram constructed and validated by us could provide a convenient and effective tool for clinicians that can improve prediction of the probability of lung metastasis in patients with ES at initial diagnosis.